[PhD] Video content security in a deep learning coding architecture

PhD open position:Title: Video content security in a deep learning coding architectureKeywords: video coding, deep learning, security of video content, confidentiality, integrity Description:Over the past few decades, numerous video compression algorithms have been developed, most based on a hybrid architecture combining transform coding and predictive coding. Standards such as H.264/AVC,…

Lire la suite

[PhD] Geometric-Semantic Adaptation of Multimodal LLMs for High-level Landmark Detection in Complex Environments

General information Description Context Landmark detection, description and matching is the cornerstone of autonomous visual localization systems deployed in unknown environments. While most widely-adopted and accurate solutions exploit low-level landmarks (i.e., points or lines), dealing with large-scale and visually ambiguous environments remains highly challenging due to the inherent multiplicity, ambiguity…

Lire la suite

[PhD] BAYESIAN RECEIVER DESIGN AND BEAMFORMING FOR MULTIUSER MIMO THZ COMMUNICATIONS USING PROBABILISTIC GRAPHICAL MODELS AND GRAPH NEURAL NETWORKS

Abstract: Wireless communications in sub-THz and THz bands are considered a key enabler for future 6G networks due to the abundance of unused spectrum and the potential for ultra-massive MIMO (UM-MIMO) systems that achieve terabit-per-second data rates and precise localization. However, challenges such as severe path loss, blockage, hardware impairments,…

Lire la suite

[PhD] ANR: On-line change detection on Lie groups for satellite attitude control

ContextDetecting abrupt changes consists in identifying the instants when the statisticalbehavior of a system changes significantly. This problem is crucial in awide range of engineering applications, where faults, environmental changes, oroperational mode switches may occur. In a real time setting, detecting suchchanges must be performed on-line, i.e. whenever a sensor…

Lire la suite

[PhD] Modèles d’apprentissage robustes et quantification de l’incertitude pour la vision par ordinateur en agriculture face aux changements de contexte (Laboratoire IMS, Bordeaux)

Contexte Le secteur agricole fait actuellement face à de nombreux défis et à des changements structurels accentués par la démographie, le changement climatique, l’impact environnemental, les modes de consommation, la compétitivité, etc. Pour y faire face, les technologies du numérique (la proxidétection/télédétection, les capteurs, le traitement du signal et des…

Lire la suite